© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6047
    Prev
    Next
    INDEX
    Explanations

    German language and academic/research-related writing, especially when discussing language itself.

    oai_token-act-pair · gemini-2.0-flash

    words related to sources or references

    np_token-act-pair-logits · gpt-4o-mini

    German language texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.57
    moveToFirst
    -0.57
     AppBundle
    -0.54
    odeon
    -0.52
     OnDestroy
    -0.52
     publick
    -0.50
    vodní
    -0.50
    RectangleBorder
    -0.50
     Cientí
    -0.49
    ValueGeneration
    -0.49
    POSITIVE LOGITS
    hoeddwyd
    0.61
    enschaften
    0.49
    saraba
    0.47
     Source
    0.47
     engraçadas
    0.46
    aume
    0.44
     SOURCE
    0.44
    Izvori
    0.43
    uisine
    0.42
     supérieures
    0.42
    Activations Density 0.406%

    No Known Activations